Developing an AI-Supported Online Assessment Platform for Islamic Religious Education Using Google Gemini AI and Google Sites

Abstract

The integration of generative artificial intelligence (AI) has the potential to improve online assessment in Islamic Religious Education (IRE) by supporting the development of interactive and Higher-Order Thinking Skills (HOTS)-oriented evaluation. This study aimed to develop and evaluate an online assessment platform integrating Google Gemini AI and Google Sites for IRE. A mixed-methods Research and Development (R&D) approach was employed using the ADDIE model, including the phases of Analysis, Design, Development, Implementation, and Evaluation. The platform was implemented with 72 senior high school students. Data were collected through expert validation, questionnaires, observations, interviews, and learning achievement tests. The findings indicate that Google Gemini AI efficiently generated contextual HOTS-based assessment items through prompt engineering, while Google Sites provided a centralized platform integrating quizzes, multimedia resources, and formative feedback. The integration improved assessment efficiency, enhanced student engagement, and supported comprehensive evaluation across cognitive, affective, and psychomotor domains. These findings suggest that AI-assisted assessment offers an effective and practical solution for digital assessment in Islamic Religious Education.